A history of randomized assignment in the social sciences

Although the concept of randomized assignment to control for extraneous factors reaches back hundreds of years, the first empirical use appears to have been in an 1835 trial of homeopathic medicine. Throughout the 19th century, there was primarily a growing awareness of the need for careful comparison groups, albeit often without the realization that randomization could be a particularly clean method to achieve that goal. In the second and more crucial phase of this history, four separate but related disciplines introduced randomized control trials within a few years of one another in the 1920s: agricultural science, clinical medicine, educational psychology, and social policy (specifically political science). Randomized control trials brought more rigor to fields that were in the process of expanding their purviews and focusing more on causal relationships. In the third phase, the 1950s through the 1970s saw a surge of interest in more applied randomized experiments in economics and elsewhere, in the lab and especially in the field.

That is from a Julian C. Jamison paper done at the World Bank, via various people in my Twitter feed.


What is random?: Chance and Order in Mathematics by Edward Beltrami (1999) is a good layman read on random. It's a fact that you don't really ever know if a number is random (as opposed to pseudo-random) unless you have an infinite sequence (the more numbers in your sequence, the better the odds of knowing if it's random). But then another phenomena presents itself: the longer the sequence, the greater the chance that you might get a very long string of non-random looking numbers hat are steadily increasing, or decreasing (Gambler's Ruin it's called, or how in the long run everything tends towards infinity or zero, at least for a while). It's all very confusing and the subject of an excellent short story "Library of Babel" by Argentine author and librarian Jorge Luis Borges (1899–1986). As a practical matter, most people use pseudo-random numbers but then another programming error occurs: often they forget to 'seed' the pseudo-random numbers with something somewhat random (like the system clock on the PC) so you get the exact same 'random looking' numbers every time you run the program, which will introduce error over time in any sample selection.

Bonus trivia: is Pi random?

There is no such thing as a random number. But, you can have numbers chosen at random and there are tools for checking random number generators.

Howdy jսst wanted to ɡive y᧐u a quick heads uр. Ꭲhe ԝords in yⲟur post ѕeem to be running
ߋff the screen in Firefox. Ι'm not sure if this iѕ a format issue οr somеthing to do
with browser compatibility Ƅut I figured I'ɗ post to let you know.
Thе design lοߋk ɡreat tһough! Hope үou ցet tһe
problem resolved ѕoon. Kudos

Awesome website you have here but I was curious about if you knew
of any community forums that cover the same topics discussed here?
I'd really like to be a part of online community where
I can get feed-back from other experienced individuals that share the same interest.
If you have any suggestions, please let me know. Many thanks!

If 'randomness' has any meaning at all, it must be an epistemic concept, not an ontological one. It's about our *ignorance*, not about properties of numbers or physical things. http://wmbriggs.com/post/2227/

That is what Einstein tried to argue when he said God doesn't play throw dice. It is an a priori conviction, but aside from personal speculation there isn't any reason why it "must" be true.

Of course there are reasons. In relation to quantum mechanics specifically, see, e.g., Jaynes's Probability in Quantum Theory (where he explains the epistemology/ontology conflation that I mentioned) or, more recently, Caticha's Entropic Dynamics, Time and Quantum Theory. If anything, the speculative conviction that probability must refer to physicial distributions at infinity (?) or 'dispositions' comes from the other side.

What is "social science"? Another academic term with which to lie by modeling taxonomic hyperbole?

Anthropology is one intellectual domain in poor shape already without the advent of "social science".

With our species having commandeered the planet for its own purposes, the lethality inherent to notions of "humanism" only now becomes apparent: death to humanism, before it kills us all.

Is there really no mention of (random) instruments in economics? (example) That seems like an important omission.

Economics is still catching up with homeopathy in many ways.

Thank you very much. i think a lot of people are looking for such a content from you. hope you will have more share such.
- slope

Randomized trials and analyses methods based on them were the best thing that ever happened to agricultural and other biological experiments. Up to the present, they have a positive track record of meaningful results.

It's record in other fields, especially where randomization of treatments is difficult it unethical, is mixed.

randomize the sociology dept and the kardashanians
send half of both of them on a 5 year sabbatical to the nullharbor plain
and film it.

frankly you are correct goolies is one l

frankly you are mansplainer

we should ask john prine
he probly knows how to spell goolies
and he will be at the
riverside theater in milwaukie
along with the middle class
next Wednesday april 25th
until then check this out
starts out with a comfortable narrative
like a malcom gladwell novel
but it takes a turn and after
10000 hours even young mr. Gladwell
notta gonna turn humptydumpty
it into another comfortable narrative
and the fellas on the lefts
guitar solo at the end
ties the whole thing together

sociology is death
death to triple bottom line accounting

until check this out

frankly I think you meant to stick this in
a little higher

Thank you so much for writing this great grace. I hope you get more from your work.

Comments for this post are closed